Polynomial functions can be realized by finite size multilayer feedforward neural networks
Authors:
- N. TodaNTN. Toda
- K.-I. FunahashiKFK.-I. Funahashi
- S. UsuiSUS. Usui
- 1 January 1991
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
No abstract availableKeywords
This publication has 8 references indexed in Scilit:
- Networks and the best approximation propertyBiological Cybernetics, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- On the approximate realization of continuous mappings by neural networksNeural Networks, 1989
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989
- Signal transformation and coding in neural systemsIEEE Transactions on Biomedical Engineering, 1989
- Learning, invariance, and generalization in high-order neural networksApplied Optics, 1987
- Nonlinear system modeling based on the Wiener theoryProceedings of the IEEE, 1981
- Polynomial Theory of Complex SystemsIEEE Transactions on Systems, Man, and Cybernetics, 1971